© 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. 3735
    Prev
    Next
    INDEX
    Explanations

    phrases related to individuals, organizations, and events appearing in a written document

    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
    227
    +0.12
    0.4%
    283
    +0.11
    0.3%
    304
    +0.11
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    227
    +0.12
    0.09
    981
    +0.11
    0.09
    143
    +0.11
    0.07
    Negative Logits
     ***!
    -0.95
     typelib
    -0.82
     تضيفلها
    -0.80
    OGND
    -0.75
    ftagPool
    -0.74
     >=",
    -0.74
     Himo
    -0.73
    ERVIS
    -0.73
    brities
    -0.72
    namientos
    -0.72
    POSITIVE LOGITS
     fta
    2.54
     reluct
    2.44
     emphat
    2.44
     thut
    2.43
     ftu
    2.37
     increa
    2.37
     disagre
    2.36
     depic
    2.36
     »>
    2.35
     fuf
    2.32
    Activations Density 0.565%

    No Known Activations