© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12650
    Prev
    Next
    INDEX
    Explanations

    notifications or details regarding a specific organization or event

    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
    1052
    +0.14
    0.5%
    897
    +0.14
    0.5%
    331
    +0.11
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1052
    +0.14
    0.10
    897
    +0.14
    0.07
    331
    +0.11
    0.07
    Negative Logits
    autogui
    -0.49
    讐
    -0.46
     psycopg
    -0.43
    SharedDtor
    -0.42
     diana
    -0.42
    Bol
    -0.41
    íqu
    -0.41
     heapq
    -0.40
    värr
    -0.39
    LayoutConstraint
    -0.38
    POSITIVE LOGITS
     FROM
    0.82
    from
    0.81
     From
    0.79
    FROM
    0.78
    From
    0.76
     from
    0.74
     từ
    0.74
     Từ
    0.67
    desde
    0.65
     afar
    0.64
    Activations Density 0.296%

    No Known Activations