© 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. 829
    Prev
    Next
    INDEX
    Explanations

    numerical values related to measurements

    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
    1385
    +0.17
    0.5%
    906
    +0.16
    0.5%
    1781
    +0.09
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1781
    +0.17
    0.03
    717
    +0.16
    0.03
    631
    +0.09
    0.01
    Negative Logits
     squa
    -1.48
     increa
    -1.47
     affor
    -1.46
     fortn
    -1.45
     inev
    -1.44
     volunte
    -1.42
     fta
    -1.42
     emphat
    -1.42
     stockholm
    -1.40
     dispen
    -1.40
    POSITIVE LOGITS
     width
    1.04
    width
    0.98
     diameter
    0.89
    Width
    0.84
     Width
    0.76
    horizontal
    0.72
    宽度
    0.72
    diameter
    0.69
     wide
    0.69
    vertical
    0.68
    Activations Density 0.145%

    No Known Activations