© 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. 6657
    Prev
    Next
    INDEX
    Explanations

    terms related to free items or services

    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
    +0.19
    1.2%
    281
    +0.12
    0.8%
    650
    +0.12
    0.7%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    281
    +0.19
    0.08
    1233
    +0.12
    0.07
    650
    +0.12
    0.06
    Negative Logits
    <bos>
    -3.35
    /*++
    -0.74
    Autoritní
    -0.71
    
    
    -0.70
    /**
    -0.66
    })();
    
    -0.65
     consider
    -0.65
     reflect
    -0.62
     bring
    -0.62
    Kontrola
    -0.62
    POSITIVE LOGITS
     maneu
    1.68
     bandung
    1.65
     increa
    1.63
     stockholm
    1.61
     Minang
    1.61
     Juf
    1.61
     milano
    1.60
     napoli
    1.59
     santiago
    1.58
     Intere
    1.58
    Activations Density 0.151%

    No Known Activations