© 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. 7563
    Prev
    Next
    INDEX
    Explanations

    content related to different types of software applications, medical conditions, and wellness activities such as yoga

    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
    394
    +0.13
    0.4%
    764
    +0.12
    0.4%
    283
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    802
    +0.13
    0.06
    227
    +0.12
    0.07
    577
    +0.11
    0.05
    Negative Logits
    GEBURTSDATUM
    -0.81
    पया
    -0.76
    QMetaType
    -0.70
    verwijspagina
    -0.70
    WithIOException
    -0.69
     stanovnika
    -0.68
    AndEndTag
    -0.67
    omores
    -0.66
     useParams
    -0.65
    rophoresis
    -0.64
    POSITIVE LOGITS
     fta
    1.76
     effe
    1.73
     fte
    1.72
     wien
    1.69
     emphat
    1.69
     Intere
    1.67
     volunte
    1.67
     inev
    1.66
     reluct
    1.66
     thut
    1.65
    Activations Density 0.485%

    No Known Activations