© 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. 1068
    Prev
    Next
    INDEX
    Explanations

    instances of a specific number repeated in sentences

    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
    776
    +0.19
    0.7%
    680
    +0.14
    0.5%
    1535
    +0.13
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    776
    +0.19
    0.07
    680
    +0.14
    0.06
    1124
    +0.13
    0.06
    Negative Logits
     dizaines
    -0.69
     centaines
    -0.63
     endeavouring
    -0.59
     decathlon
    -0.55
     gaily
    -0.55
     prochaines
    -0.52
     starlight
    -0.52
     milliers
    -0.52
     snapback
    -0.52
     melange
    -0.51
    POSITIVE LOGITS
    TWO
    0.85
    two
    0.83
     two
    0.74
    Two
    0.73
     TWO
    0.72
     Two
    0.67
    thirds
    0.65
     zwei
    0.63
    stwo
    0.62
    three
    0.59
    Activations Density 0.151%

    No Known Activations