© 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. 13933
    Prev
    Next
    INDEX
    Explanations

    sentences describing a character's experiences and thoughts

    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
    50
    +0.11
    0.3%
    1577
    +0.10
    0.3%
    1533
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1533
    +0.11
    0.01
    184
    +0.10
    0.02
    194
    +0.10
    0.02
    Negative Logits
     milano
    -1.20
     „,
    -1.19
     embra
    -1.11
     hcm
    -1.09
     increa
    -1.09
     voleva
    -1.09
     guarante
    -1.09
     dispen
    -1.08
     robus
    -1.08
     doman
    -1.08
    POSITIVE LOGITS
     knew
    0.93
     hadn
    0.91
     had
    0.86
     was
    0.80
     seemed
    0.80
     wasn
    0.79
    had
    0.74
     were
    0.72
     couldn
    0.72
    knew
    0.71
    Activations Density 1.541%

    No Known Activations