© 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. 3306
    Prev
    Next
    INDEX
    Explanations

    text related to the interpretation or meaning of statements or actions

    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
    573
    +0.11
    0.4%
    1677
    +0.10
    0.4%
    316
    +0.10
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1601
    +0.11
    0.02
    662
    +0.10
    0.02
    1677
    +0.10
    0.02
    Negative Logits
     Kün
    -0.79
     Chaves
    -0.57
     Requis
    -0.56
     Gies
    -0.54
     Heere
    -0.54
     Diez
    -0.54
    shutterstock
    -0.54
     Knud
    -0.52
     shutterstock
    -0.52
     ciasc
    -0.52
    POSITIVE LOGITS
     interpretation
    1.19
     interpret
    1.18
    interpretation
    1.13
     interpretations
    1.09
     interpreted
    1.06
    interpret
    1.04
     INTERPRET
    1.01
     Interpretation
    1.00
     interpreting
    1.00
     interpreta
    0.98
    Activations Density 0.096%

    No Known Activations