© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 14182
    Prev
    Next
    INDEX
    Explanations

    the possessive form of words

    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
    674
    +0.14
    0.4%
    1967
    +0.12
    0.4%
    1505
    +0.12
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1505
    +0.14
    0.04
    1310
    +0.12
    0.03
    421
    +0.12
    0.03
    Negative Logits
     thut
    -1.37
     ftu
    -1.14
     effe
    -1.11
     fte
    -1.10
     fup
    -1.10
     overla
    -1.09
     fta
    -1.08
     foon
    -1.07
     maneu
    -1.05
     »>
    -1.04
    POSITIVE LOGITS
     largest
    0.67
     finest
    0.64
     greatest
    0.63
     biggest
    0.61
    ghest
    0.60
     most
    0.59
     best
    0.57
     oldest
    0.57
    s
    0.57
     world
    0.56
    Activations Density 0.089%

    No Known Activations