© 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. 12881
    Prev
    Next
    INDEX
    Explanations

    texts related to a specific coding example but seems to be particularly activated by words related to embarrassment or discomfort

    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
    131
    +0.18
    0.8%
    757
    +0.17
    0.7%
    1810
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    757
    +0.18
    0.04
    131
    +0.17
    0.02
    1778
    +0.13
    0.02
    Negative Logits
     unspeak
    -0.51
     unlaw
    -0.49
     predominate
    -0.47
    attenzione
    -0.46
     misread
    -0.46
     perpetuated
    -0.45
    ナソニック
    -0.45
     precluded
    -0.45
     shewn
    -0.44
     incarcer
    -0.43
    POSITIVE LOGITS
     Amb
    1.29
    Amb
    1.23
     amb
    1.08
    amb
    1.02
     Ambro
    0.98
    AMB
    0.86
     Ambrose
    0.82
     serai
    0.81
     Kamb
    0.76
     Ambition
    0.74
    Activations Density 0.143%

    No Known Activations