© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 7489
    Prev
    Next
    INDEX
    Explanations

    mentions of specific language-related content and programming concepts, such as Java, PHP, and testing frameworks

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-IT-Residual-Stream-SAEs/gemma_2b_it_blocks.12.hook_resid_post_16384
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    standard
    Context Size
    1,024
    Dataset
    Skylion007/openwebtext
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    1741
    +0.16
    0.5%
    1984
    +0.13
    0.4%
    120
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1984
    +0.16
    0.03
    368
    +0.13
    0.02
    120
    +0.12
    0.02
    Negative Logits
    rungsseite
    -0.71
    typeDefinition
    -0.63
     censiti
    -0.61
    Clik
    -0.61
    EndProject
    -0.59
    Демографія
    -0.58
     BoxFit
    -0.56
    principalTable
    -0.55
     OMIT
    -0.55
    errHandler
    -0.55
    POSITIVE LOGITS
     overla
    0.84
     ricardo
    0.83
     suscep
    0.82
     jorge
    0.76
    Java
    0.76
     fluo
    0.75
     alberto
    0.74
     javier
    0.72
     leonardo
    0.72
     franz
    0.72
    Activations Density 0.090%

    No Known Activations