© 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 SAEs
    5. Gemma-2B
    7. Residual Stream
    9. 6-RES-JB
    11. 6485
    Prev
    Next
    INDEX
    Explanations

    applications for programs or positions and information about eligibility and requirements

    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
    +0.21
    0.8%
    1226
    +0.07
    0.3%
    1150
    +0.07
    0.3%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    792
    +0.21
    0.04
    1226
    +0.07
    0.04
    1887
    +0.07
    0.04
    Negative Logits
    <bos>
    -2.67
    Pyx
    -0.71
     ldc
    -0.69
    ുറ
    -0.68
    CodeDom
    -0.67
    endif
    -0.66
    },[])
    -0.66
    mappedBy
    -0.65
     colspan
    -0.64
    imanapun
    -0.64
    POSITIVE LOGITS
     maneu
    2.45
     impra
    2.25
     affor
    2.20
     increa
    2.19
     reluct
    2.13
     shenan
    2.11
     accla
    2.05
     apprehen
    2.03
     disagre
    2.02
     uninten
    2.00
    Activations Density 0.420%

    No Known Activations