© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 3764
    Prev
    Next
    INDEX
    Explanations

    legal terms and concepts related to rights and regulations

    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
    1177
    +0.09
    0.3%
    391
    +0.08
    0.2%
    198
    +0.08
    0.2%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    100
    +0.09
    0.04
    1328
    +0.08
    0.04
    208
    +0.08
    0.05
    Negative Logits
     unspeak
    -0.88
     apprehen
    -0.84
     ineffec
    -0.76
     laug
    -0.76
     intersper
    -0.75
     shenan
    -0.75
     impra
    -0.75
     disagre
    -0.73
     reluct
    -0.73
     pooh
    -0.72
    POSITIVE LOGITS
     noten
    0.66
     kug
    0.66
     kask
    0.65
     institut
    0.63
     kolon
    0.60
     usta
    0.60
     makro
    0.60
     plak
    0.59
     kade
    0.59
     akut
    0.57
    Activations Density 0.352%

    No Known Activations