© 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. 254
    Prev
    Next
    INDEX
    Explanations

    descriptions of a person's appearance and background in an interview setting

    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
    2015
    +0.12
    0.5%
    897
    +0.10
    0.4%
    1896
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    2015
    +0.12
    -0.01
    184
    +0.10
    -0.08
    1784
    +0.10
    0.10
    Negative Logits
    <bos>
    -2.72
     intersper
    -1.69
     encomp
    -1.45
     shenan
    -1.24
     apprehen
    -1.22
     reluct
    -1.16
     depic
    -1.16
     gild
    -1.11
    /***
    -1.10
     endow
    -1.09
    POSITIVE LOGITS
     tanong
    0.90
    ]=="
    0.80
     getNome
    0.77
    Sklici
    0.76
    ]!='
    0.71
    según
    0.71
    Život
    0.71
     sarili
    0.71
     ameste
    0.71
    Trayectoria
    0.70
    Activations Density 5.130%

    No Known Activations