© 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. 12846
    Prev
    Next
    INDEX
    Explanations

    descriptions of powerful and destructive energy events

    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
    906
    +0.17
    0.5%
    736
    +0.16
    0.5%
    604
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.17
    0.08
    946
    +0.16
    0.05
    724
    +0.13
    0.04
    Negative Logits
     silikon
    -1.43
     alkoh
    -1.42
     praktik
    -1.34
     anse
    -1.33
     lele
    -1.32
     makro
    -1.32
     solidar
    -1.32
     roba
    -1.30
     antik
    -1.30
     konserv
    -1.30
    POSITIVE LOGITS
     ineffectual
    0.69
    Gdzie
    0.64
    Czym
    0.64
    Dlaczego
    0.62
     treachery
    0.62
     yerde
    0.59
     odious
    0.59
     belliger
    0.59
     barbarous
    0.58
     opět
    0.58
    Activations Density 0.345%

    No Known Activations