© 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. 14102
    Prev
    Next
    INDEX
    Explanations

    descriptions of basketball players and their statistics

    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
    1385
    +0.10
    0.3%
    964
    +0.10
    0.3%
    645
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1110
    +0.10
    0.02
    480
    +0.10
    0.02
    1654
    +0.09
    0.02
    Negative Logits
     encomp
    -1.35
     fortn
    -1.31
     fep
    -1.29
     squa
    -1.23
     fta
    -1.21
     ftu
    -1.20
     affor
    -1.19
     thut
    -1.19
     increa
    -1.18
     Intere
    -1.18
    POSITIVE LOGITS
    height
    0.79
     tall
    0.78
     height
    0.75
    Height
    0.67
    tall
    0.62
     Height
    0.58
    <bos>
    0.58
    foot
    0.58
    getHeight
    0.54
    útbol
    0.53
    Activations Density 0.055%

    No Known Activations