© 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
    2. Joseph Bloom · Initial Gemma-2B-IT SAEs
    3. Gemma-2B-IT
    4. Residual Stream
    5. 12-RES-JB
    6. 3777
    Prev
    Next
    INDEX
    Explanations

    descriptions of numerical values and coding-related content

    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
    1535
    +0.24
    0.8%
    2034
    +0.21
    0.7%
    1699
    +0.19
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    382
    +0.24
    0.04
    1535
    +0.21
    0.04
    1150
    +0.19
    0.02
    Negative Logits
     viciss
    -1.74
     inev
    -1.72
     suspic
    -1.68
     vagu
    -1.67
     inconce
    -1.65
     shenan
    -1.64
     affor
    -1.64
     increa
    -1.62
     nece
    -1.61
     volunte
    -1.61
    POSITIVE LOGITS
    <eos>
    1.45
    ↵↵
    1.42
    ↵↵↵
    1.27
    ↵
    1.18
    ↵↵↵↵
    1.15
    ↵↵↵↵↵
    1.09
    <bos>
    1.01
    </tr>
    0.98
    }.
    0.96
    0.96
    Activations Density 0.085%

    No Known Activations