© 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. 14442
    Prev
    Next
    INDEX
    Explanations

    descriptions and instructions related to mechanics or technical processes involving tools

    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
    +0.19
    0.6%
    1385
    +0.15
    0.5%
    184
    +0.13
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    724
    +0.19
    0.05
    736
    +0.15
    0.06
    2044
    +0.13
    0.06
    Negative Logits
     Jerusal
    -1.10
     konserv
    -1.10
     monaster
    -1.09
     Palest
    -1.08
     alkoh
    -1.07
     Meksi
    -1.07
     republi
    -1.06
     allarg
    -1.04
     Lombar
    -1.03
     tramont
    -1.02
    POSITIVE LOGITS
     trakcie
    0.56
     umgeben
    0.54
     ciągu
    0.54
     inside
    0.53
     gondol
    0.53
     zakresie
    0.53
     itself
    0.52
     veliko
    0.52
     peintures
    0.51
     bedeckt
    0.51
    Activations Density 0.314%

    No Known Activations