© 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 SAEs
    3. Gemma-2B
    4. Residual Stream
    5. 6-RES-JB
    6. 351
    Prev
    Next
    INDEX
    Explanations

    descriptions related to gathering or joining groups for shared interests or activities

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/Gemma-2b-Residual-Stream-SAEs/gemma_2b_blocks.6.hook_resid_post_16384_anthropic_fast_lr
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    HuggingFaceFW/fineweb
    Features
    16,384
    Data Type
    torch.float32
    Hook Point
    blocks.6.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    HuggingFaceFW/fineweb
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    50
    +0.23
    0.8%
    678
    +0.09
    0.3%
    783
    +0.08
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    1916
    +0.23
    0.07
    783
    +0.09
    0.07
    7
    +0.08
    0.07
    Negative Logits
    <bos>
    -2.34
    ValueGenerated
    -0.84
    Autoritní
    -0.83
    HasIndex
    -0.81
    RotationOrder
    -0.78
     createState
    -0.74
     MenuView
    -0.73
     ISNI
    -0.72
    ftagPool
    -0.72
    PutMapping
    -0.71
    POSITIVE LOGITS
     impra
    2.08
     affor
    2.00
     impractica
    1.99
     increa
    1.97
     unlaw
    1.97
     reluct
    1.95
     Intere
    1.85
     unden
    1.83
     maneu
    1.80
     suscep
    1.78
    Activations Density 1.362%

    No Known Activations