© 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. 13899
    Prev
    Next
    INDEX
    Explanations

    technical details and descriptions related to tools or procedures

    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
    +0.14
    0.4%
    1531
    +0.10
    0.3%
    604
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2044
    +0.14
    0.05
    1531
    +0.10
    0.04
    1791
    +0.09
    0.03
    Negative Logits
    <bos>
    -0.92
     Öster
    -0.83
     maksi
    -0.81
     Keny
    -0.79
     lü
    -0.79
     keramik
    -0.78
     uhr
    -0.77
     territo
    -0.74
     panik
    -0.73
     Heeren
    -0.71
    POSITIVE LOGITS
     requires
    0.68
     require
    0.66
     disadvantages
    0.65
     disadvantage
    0.64
    Lmfao
    0.60
     Requires
    0.59
     drawback
    0.59
     tricot
    0.59
    sightly
    0.59
     expensive
    0.58
    Activations Density 0.384%

    No Known Activations