© 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. 14487
    Prev
    Next
    INDEX
    Explanations

    that both sentences start with a number followed by a word

    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
    1967
    +0.15
    0.6%
    866
    +0.15
    0.6%
    47
    +0.15
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    47
    +0.15
    0.07
    1937
    +0.15
    0.07
    866
    +0.15
    0.05
    Negative Logits
    PathParam
    -0.50
     would
    -0.48
     will
    -0.45
     وصلة
    -0.45
    -
    -0.44
     and
    -0.44
    lut
    -0.43
    ’
    -0.43
     could
    -0.42
     I
    -0.42
    POSITIVE LOGITS
     eccellente
    0.87
     abbra
    0.87
     ridu
    0.82
     kasama
    0.77
     aimable
    0.77
     piacevole
    0.77
     pecuni
    0.76
     churrasco
    0.76
    🕗
    0.74
     riemp
    0.74
    Activations Density 0.257%

    No Known Activations