© 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. 3550
    Prev
    Next
    INDEX
    Explanations

    items and steps in a list or guide

    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
    876
    +0.18
    0.6%
    1343
    +0.14
    0.5%
    1150
    +0.14
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.18
    0.05
    1385
    +0.14
    0.04
    678
    +0.14
    0.04
    Negative Logits
     akut
    -1.18
     alkoh
    -1.15
     kemer
    -1.12
     Rumania
    -1.11
     maksi
    -1.11
     praktik
    -1.10
     ekos
    -1.09
     panik
    -1.08
     protokol
    -1.07
     Keny
    -1.06
    POSITIVE LOGITS
     derselbe
    0.68
     mocht
    0.64
    használ
    0.61
     brengt
    0.60
     heet
    0.60
     gră
    0.60
     namentlich
    0.59
     bleek
    0.59
     ochi
    0.59
     hoort
    0.58
    Activations Density 0.286%

    No Known Activations