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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Initial Gemma-2B-IT SAEs
    5. Gemma-2B-IT
    7. Residual Stream
    9. 12-RES-JB
    11. 3800
    Prev
    Next
    INDEX
    Explanations

    language related to providing instructions or guidance

    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
    994
    +0.11
    0.4%
    468
    +0.10
    0.3%
    1262
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    468
    +0.11
    0.06
    316
    +0.10
    0.06
    994
    +0.09
    0.05
    Negative Logits
     lele
    -1.07
     saar
    -1.00
     alip
    -1.00
     maksi
    -0.97
     franz
    -0.96
     uhr
    -0.96
     dises
    -0.93
     hina
    -0.93
     kram
    -0.92
     jep
    -0.92
    POSITIVE LOGITS
     this
    0.75
     kind
    0.70
     type
    0.70
     particular
    0.69
    this
    0.68
     same
    0.66
     aspect
    0.65
     latter
    0.65
     This
    0.65
     THIS
    0.64
    Activations Density 0.221%

    No Known Activations